Author of the publication

Please choose a person to relate this publication to

To differ between persons with the same name, the academic degree and the title of an important publication will be displayed. You can also use the button next to the name to display some publications already assigned to the person.

 

Other publications of authors with the same name

ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness., , , , , and . ICLR, OpenReview.net, (2019)Fast Minimum-norm Adversarial Attacks through Adaptive Norm Constraints., , , and . NeurIPS, page 20052-20062. (2021)On Adaptive Attacks to Adversarial Example Defenses., , , and . NeurIPS, (2020)Towards Nonlinear Disentanglement in Natural Data with Temporal Sparse Coding., , , , , , and . ICLR, OpenReview.net, (2021)Visual Representation Learning Does Not Generalize Strongly Within the Same Domain., , , , , , , , and . ICLR, OpenReview.net, (2022)Does CLIP's generalization performance mainly stem from high train-test similarity?, , , , and . ICLR, OpenReview.net, (2024)Position: Understanding LLMs Requires More Than Statistical Generalization., , , , , and . ICML, OpenReview.net, (2024)Translational symmetry in convolutions with localized kernels causes an implicit bias toward high frequency adversarial examples., , , , , , and . Frontiers Comput. Neurosci., (2024)What does it take to generate natural textures?, , , and . ICLR (Poster), OpenReview.net, (2017)Approximating CNNs with Bag-of-local-Features models works surprisingly well on ImageNet., and . ICLR (Poster), OpenReview.net, (2019)